# ML-DL-RL-AutoML

**Repository Path**: mapicccy/ML-DL-RL-AutoML

## Basic Information

- **Project Name**: ML-DL-RL-AutoML
- **Description**: machine learning/deep learning/reinforcement learning/autoML
- **Primary Language**: Python
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2021-10-17
- **Last Updated**: 2021-10-17

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# ML-DL-RL-AutoML
machine learning/deep learning/reinforcement learning/autoML

## ML

## DL

## RL
Up to now, implementing Q-learning\DQN\DDQN\Actor-Critic\DDPG.

Further more, approving a general theory, The Worst is the Best, which improved DQN\DDQN\Actor-Critic on openai gym environment.

This theory is for NIPS-2018, and the code is under the directory 'ML-DL-RL-AutoML/RL/RL-extend-for-NIPS2018-paper'.

[Read more](./RL/README.md)

## AutoML
Up to now, implementing traditional bayesian and gaussion process regressor by sklearn and skopt

[Read more](./autoML/README.md)